run_web_harvest · FlashLeads MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_web_harvest does on FlashLeads MCP Server

AI agents invoke run_web_harvest to trigger actions in FlashLeads MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_web_harvest needs a policy

This tool executes an external operation (Google search + web scraping) and automatically creates or modifies a persistent agent on the server. It goes beyond a simple read because it triggers active crawling infrastructure and has side effects (creating/updating harvest agents). The blast radius is high because misuse could initiate large-scale scraping campaigns, consume API quotas, or collect data inappropriately.

From the tool's definition 'Search Google and collect company website leads. Automatically creates or updates your web harvest agent.' — triggers an external web harvesting operation, creates/updates an agent, and scrapes data from Google and company websites.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_web_harvest Rate-limited

run_web_harvest stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_web_harvest": {
      "limits": [
        {
          "counter": "run_web_harvest_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches FlashLeads MCP Server, so you can run agents against it safely.

FAQ

Questions about run_web_harvest

What does the run_web_harvest tool do? +

Search Google and collect company website leads. Automatically creates or updates your web harvest agent. Returns leads with company names, websites, emails, phone numbers, and social media profiles. It is categorised as a Execute tool in the FlashLeads MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_web_harvest? +

Register the FlashLeads MCP Server MCP server in PolicyLayer and add a rule for run_web_harvest: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches FlashLeads MCP Server. Nothing to install.

What risk level is run_web_harvest? +

run_web_harvest is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_web_harvest? +

Yes. Add a rate_limit block to the run_web_harvest rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block run_web_harvest completely? +

Set action: deny in the PolicyLayer policy for run_web_harvest. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides run_web_harvest? +

run_web_harvest is provided by the FlashLeads MCP Server MCP server (mohamad-zubi/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.